AI VOICE CHATTING TO HELP WITH CUSTOMER SUPPORT USE-CASES

Using current speech augmented LLMs (SpeechLLMs) with realtime voice modality to understand user issues and to provide support and solutions.

Using Realtime speech LLMs to assist with service requests

Provide solutions and raise service tickets.

App link : techvistara-ai-voice.azurewebsites.net

Initial Architecture - Version V1

Link to the architecture diagram : User draw.io to render

alt text

High level initial implementation for version 1 , later we will introduce chat like functionality, having context to the model on the topic, raising service tickets.(in future blogs)

Part 1 : Recording audio from user and generating a audio file

Using replit agent created a voice recording flask app which we can leverage

replit-voice-recorder

alt text

gunicorn --bind 0.0.0.0:$PORT main:app

deployment-success

Link : https://techvistara-ai-voice.azurewebsites.net/

running-app

Flow diagram until completed portion

alt text

Next steps

Generating text from the generated audio file from the user

Building - Next steps

coming soon

Back to home